AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Render-to-Adapt: Unsupervised Personal Adaptation for Gaze Estimation

Yangshi Ge, Zheng Liu, Feng Lu

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add iris task during pre-training (oma) (ablation)ResNet-18 gaze estimator · DE→DMangular error (deg): 8.75 -> 7.23Improved
add iris pre-finetuning on rendered images (js) (ablation)ResNet-18 + oma · DE→DMangular error (deg): 7.23 -> 6.29Improved
add self-supervised render-cycle calibration loop (sg) (ablation)ResNet-18 + oma + js · DE→DMangular error (deg): 6.29 -> 4.84Improved
add Lcycle on top of Lanchor (ablation)R2A · DE→DMangular error (deg): 6.29 -> 4.84Improved
add Lanchor on top of Lcycle (ablation)R2A · DE→DMangular error (deg): 5.21 -> 4.84Improved
increase unlabeled calibration images from 1 to 10 (ablation)R2A · DE→DMangular error (deg): 5.78 -> 4.84Improved
increase unlabeled calibration images from 10 to 20 (ablation)R2A · DE→DMangular error (deg): 4.84 -> 4.77No clear effect
use GazeGaussian instead of GazeNeRF as the differentiable renderer (ablation)R2A · DE→DMangular error (deg): 5.13 -> 4.84Improved
use ResNet-50 backbone instead of ResNet-18 (ablation)R2A · DE→DMangular error (deg): 4.84 -> 4.64Improved
apply UDA methods (PnP-GA, UnReGA) per individual instead of on the populationUnReGA · DE→DMangular error (deg): 5.11 -> 5.72Hurt
R2A unsupervised versus supervised personal fine-tuningR2A · DG→DMangular error (deg): 5.38 -> 4.92Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy